• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.136-146
• /
• 2022

Some surface defects make the weak quality of steel materials. To limit these defects, we advocate a one-stage detector model RetinaNet among diverse detection algorithms in deep learning. There are several backbones in the RetinaNet model. We acknowledged two backbones, which are ResNet50 and VGG19. To validate our model, we compared and analyzed several traditional models, one-stage models like YOLO and SSD models and two-stage models like Faster-RCNN, EDDN, and Xception models, with simulations based on steel individual classes. We also performed the correlation of the time factor between one-stage and two-stage models. Comparative analysis shows that the proposed model achieves excellent results on the dataset of the Northeastern University surface defect detection dataset. We would like to work on different backbones to check the efficiency of the model for real world, increasing the datasets through augmentation and focus on improving our limitation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.317-326
• /
• 2024

Biometric recognition is a technology that determines whether a person is identified by extracting information on a person's biometric and behavioral characteristics with a specific device. Cyber threats such as forgery, duplication, and hacking of biometric characteristics are increasing in the field of biometrics. In response, the security system is strengthened and complex, and it is becoming difficult for individuals to use. To this end, multiple biometric models are being studied. Existing studies have suggested feature fusion methods, but comparisons between feature fusion methods are insufficient. Therefore, in this paper, we compared and evaluated the fusion method of multiple biometric models using fingerprint, face, and iris images. VGG-16, ResNet-50, EfficientNet-B1, EfficientNet-B4, EfficientNet-B7, and Inception-v3 were used for feature extraction, and the fusion methods of 'Sensor-Level', 'Feature-Level', 'Score-Level', and 'Rank-Level' were compared and evaluated for feature fusion. As a result of the comparative evaluation, the EfficientNet-B7 model showed 98.51% accuracy and high stability in the 'Feature-Level' fusion method. However, because the EfficietnNet-B7 model is large in size, model lightweight studies are needed for biocharacteristic fusion.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.83-86
• /
• 2019

도시화 과정에서 도시의 생활폐기물 문제가 빠르게 증가되고 있고, 효과적이지 못한 생활폐기물 관리는 도시의 오염을 악화시키고 물리적인 환경오염과 경제적인 부분에서 극심한 문제들을 야기시킬 수 있다. 게다가 부피가 커서 관리하기 힘든 대형 생활폐기물들이 증가하여 도시 발전에도 방해가 된다. 생활폐기물을 처리하는데 있어 대형 생활폐기물 품목에 대해서는 요금을 청구하여 처리한다. 다양한 유형의 대형 생활폐기물을 수동으로 분류하는 것은 시간과 비용이 많이 든다. 그 결과 대형 생활폐기물을 자동으로 분류하는 시스템을 도입하는 것이 중요하다. 본 논문에서는 대형 생활폐기물 분류를 위한 시스템을 제안하며, 이 논문의 4 가지로 분류된다. 1) 높은 정확도와 강 분류(roust classification) 수행에 적합한 Convolution Neural Network(CNN) 모델 중 VGG-19, Inception-V3, ResNet50 의 정확도와 속도를 비교한다. 제안된 20 개의 클래스의 대형 생활폐기물의 데이터 셋(data set)에 대해 가장 높은 분류의 정확도는 86.19%이다. 2) 불균형 데이터 문제를 처리하기 Class Weight VGG-19(CW-VGG-19)와 Extreme Gradient Boosting VGG-19 두 가지 방법을 사용하였다. 3) 20 개의 클래스를 포함하는 데이터 셋을 수동으로 수집 및 검증하였으며 각 클래스의 컬러 이미지 수는 500 개 이상이다. 4) 딥 러닝(Deep Learning) 기반 모바일 애플리케이션을 개발하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.522-524
• /
• 2019

In spite of a rapid development in the quality of built-in mobile cameras, their some physical restrictions hinder them to achieve the satisfactory results of digital single lens reflex (DSLR) cameras. In this work we propose an end-to-end deep learning method to translate ordinary images by mobile cameras into DSLR-quality photos. The method is based on the framework of generative adversarial networks (GANs) with several improvements. First, we combined the U-Net with DenseNet and connected dense block (DB) in terms of U-Net. The Dense U-Net acts as the generator in our GAN model. Then, we improved the perceptual loss by using the VGG features and pixel-wise content, which could provide stronger supervision for contrast enhancement and texture recovery.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.778-789
• /
• 2021

Recently, various lightweight methods for using Convolutional Neural Network(CNN) models in mobile devices have emerged. Weight quantization, which lowers bit precision of weights, is a lightweight method that enables a model to be used through integer calculation in a mobile environment where GPU acceleration is unable. Weight quantization has already been used in various models as a lightweight method to reduce computational complexity and model size with a small loss of accuracy. Considering the size of memory and computing speed as well as the storage size of the device and the limited network environment, this paper proposes a method of compressing integer weights after quantization using a video codec as a method. To verify the performance of the proposed method, experiments were conducted on VGG16, Resnet50, and Resnet18 models trained with ImageNet and Places365 datasets. As a result, loss of accuracy less than 2% and high compression efficiency were achieved in various models. In addition, as a result of comparison with similar compression methods, it was verified that the compression efficiency was more than doubled.

• Journal of Animal Science and Technology
• /
• v.63 no.2
• /
• pp.367-379
• /
• 2021

The objectives of this study were to evaluate convolutional neural network models and computer vision techniques for the classification of swine posture with high accuracy and to use the derived result in the investigation of the effect of dietary fiber level on the behavioral characteristics of the pregnant sow under low and high ambient temperatures during the last stage of gestation. A total of 27 crossbred sows (Yorkshire × Landrace; average body weight, 192.2 ± 4.8 kg) were assigned to three treatments in a randomized complete block design during the last stage of gestation (days 90 to 114). The sows in group 1 were fed a 3% fiber diet under neutral ambient temperature; the sows in group 2 were fed a diet with 3% fiber under high ambient temperature (HT); the sows in group 3 were fed a 6% fiber diet under HT. Eight popular deep learning-based feature extraction frameworks (DenseNet121, DenseNet201, InceptionResNetV2, InceptionV3, MobileNet, VGG16, VGG19, and Xception) used for automatic swine posture classification were selected and compared using the swine posture image dataset that was constructed under real swine farm conditions. The neural network models showed excellent performance on previously unseen data (ability to generalize). The DenseNet121 feature extractor achieved the best performance with 99.83% accuracy, and both DenseNet201 and MobileNet showed an accuracy of 99.77% for the classification of the image dataset. The behavior of sows classified by the DenseNet121 feature extractor showed that the HT in our study reduced (p < 0.05) the standing behavior of sows and also has a tendency to increase (p = 0.082) lying behavior. High dietary fiber treatment tended to increase (p = 0.064) lying and decrease (p < 0.05) the standing behavior of sows, but there was no change in sitting under HT conditions.

• International Journal of Computer Science & Network Security
• /
• v.21 no.7
• /
• pp.324-330
• /
• 2021

Agriculture is one of the essential needs of human life on planet Earth. It is the source of food and earnings for many individuals around the world. The economy of many countries is associated with the agriculture sector. Lots of diseases exist that attack various fruits and crops. Apple Tree Leaves also suffer different types of pathological conditions that affect their production. These pathological conditions include apple scab, cedar apple rust, or multiple diseases, etc. In this paper, an automatic detection framework based on deep learning is investigated for apple leaves disease classification. Different pre-trained models, VGG16, ResNetV2, InceptionV3, and MobileNetV2, are considered for transfer learning. A combination of parameters like learning rate, batch size, and optimizer is analyzed, and the best combination of ResNetV2 with Adam optimizer provided the best classification accuracy of 94%.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.101-110
• /
• 2022

Histopathological analysis of biopsy specimens is still used for diagnosis and classifying the brain tumors today. The available procedures are intrusive, time consuming, and inclined to human error. To overcome these disadvantages, need of implementing a fully automated deep learning-based model to classify brain tumor into multiple classes. The proposed CNN model with an accuracy of 92.98 % for categorizing tumors into five classes such as normal tumor, glioma tumor, meningioma tumor, pituitary tumor, and metastatic tumor. Using the grid search optimization approach, all of the critical hyper parameters of suggested CNN framework were instantly assigned. Alex Net, Inception v3, Res Net -50, VGG -16, and Google - Net are all examples of cutting-edge CNN models that are compared to the suggested CNN model. Using huge, publicly available clinical datasets, satisfactory classification results were produced. Physicians and radiologists can use the suggested CNN model to confirm their first screening for brain tumor Multi-classification.

• The Journal of Society for e-Business Studies
• /
• v.26 no.2
• /
• pp.19-43
• /
• 2021

The prediction of box office performance in performing arts institutions is an important issue in the performing arts industry and institutions. For this, traditional prediction methodology and data mining methodology using standardized data such as cast members, performance venues, and ticket prices have been proposed. However, although it is evident that audiences tend to seek out their intentions by the performance guide poster, few attempts were made to predict box office performance by analyzing poster images. Hence, the purpose of this study is to propose a deep learning application method that can predict box office success through performance-related poster images. Prediction was performed using deep learning algorithms such as Pure CNN, VGG-16, Inception-v3, and ResNet50 using poster images published on the KOPIS as learning data set. In addition, an ensemble with traditional regression analysis methodology was also attempted. As a result, it showed high discrimination performance exceeding 85% of box office prediction accuracy. This study is the first attempt to predict box office success using image data in the performing arts field, and the method proposed in this study can be applied to the areas of poster-based advertisements such as institutional promotions and corporate product advertisements.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.9-17
• /
• 2024

Due to the recent pandemic and the development of ICT technology, the use of non-face-to-face and unmanned systems is expanding, and it is very important to understand emotions in communication in non-face-to-face situations. As emotion recognition methods for various facial expressions are required to understand emotions, artificial intelligence-based research is being conducted to improve facial expression emotion recognition in image data. However, existing research on facial expression emotion recognition requires high computing power and a lot of learning time because it utilizes a large amount of data to improve accuracy. To improve these limitations, this paper proposes a method of recognizing facial expressions using age and gender, which are image meta information, as a method of recognizing facial expressions with even a small amount of data. For facial expression emotion recognition, a face was detected using the Yolo Face model from the original image data, and age and gender were classified through the VGG model based on image meta information, and then seven emotions were recognized using the EfficientNet model. The accuracy of the proposed data classification learning model was higher as a result of comparing the meta-information-based data classification model with the model trained with all data.